Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add charlieviettq/awesome-agent-skill --skill doubt-driven-reviewgit clone --depth 1 https://github.com/charlieviettq/awesome-agent-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/charlieviettq/awesome-agent-skill/doubt-driven-review)<a href="https://agentmods.dev/skills/charlieviettq/awesome-agent-skill/doubt-driven-review"><img src="https://agentmods.dev/badge/skills/charlieviettq/awesome-agent-skill/doubt-driven-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/charlieviettq/awesome-agent-skill/doubt-driven-review"><img src="https://agentmods.dev/badge/skills/charlieviettq/awesome-agent-skill/doubt-driven-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00042 | $0.00341 |
| Opus 5.5 | $0.00017 | $0.00136 |
| Sonnet 5.5 | $0.00008 | $0.00068 |
| Haiku 4.5 | $0.00004 | $0.00034 |
Grade A, and why
doubt-driven-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Doubt-driven review
Non-trivial when
- Branching logic or cross-module boundary changes
- Properties types/compiler cannot verify
- Irreversible deploy, migration, or public API change
When not to use
- Renames, formatting, obvious one-liners
Cycle
- CLAIM — decision + why it matters (2-3 lines)
- EXTRACT — artifact + contract only (no reasoning journey)
- DOUBT — fresh review with adversarial prompt ("find issues, do not validate")
- RECONCILE — classify: contract misread / actionable / trade-off / noise
- STOP — trivial findings only, 3 cycles max, or user says ship
Reviewer input
Pass ARTIFACT + CONTRACT only—not your CLAIM (avoids agreement bias).
Reconcile precedence
- Contract misread — fix contract, re-run
- Valid actionable — change artifact
- Valid trade-off — document explicitly
- Noise — note and move on
Optional second opinion
Offer cross-model or codex review for high stakes; user decides. Never silent skip.
Related
verify-before-done, test-first-development (RED step as behavioral doubt), gstack/review (post-hoc PR)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 45 lines · 42 tokens per session scan A de7f6ed90ca3
doubt-driven-review is a skill published in the GitHub repository charlieviettq/awesome-agent-skill (26 stars, last pushed 3mo ago), licensed MIT. It adds 42 tokens to every session and 341 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
refactor-advisor
A code review helper that finds common design and maintenance problems in a codebase and suggests ways to restructure the code.
zh-code-reviewer
A Chinese-language code-review specialist that produces a structured review report. It examines coding style, possible bugs, performance, security, and design choices.
luna
Reviews code for objective correctness, security, and reliability.
max
Cleans up and improves existing code without changing behavior.
address-github-comments
Use when you need to address review or issue comments on an open GitHub Pull Request using the gh CLI.
andrej-karpathy
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.